检索结果-内蒙古大学图书馆

9th IEEE data driven Control and Learning Systems Conference (DDCLS)

作者： Wang, Yu Bai, Xuejian Cheng, Long Wang, Shuo Tan, Min Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China CAS Ctr Excellence Brain Sci & Intelligence Techn Shanghai 200031 Peoples R China

ISBN: (纸本)9781728159225

In this study, a data-driven hydrodynamic modeling method for a flippers-driven underwater vehicle-manipulator system (F-UVMS) is proposed. The modeling method combines parameter identification technique and computational fluid dynamics simulation, which makes the acquisition of hydrodynamic coefficients efficient and convenient. The hydrodynamic analysis of the biomimetic flipper propulsor is completed and the relationships between the generated forces and the motion parameters of the biomimetic flipper propulsor are revealed. The wake effects are analyzed to reveal the mechanism of the biomimetic flipper propulsor. Lift and drag coefficients are identified by the hydrodynamic data and the dynamic model of the biomimetic flipper propulsor is derived. The proposed hydrodynamic model is applied to the position control strategy of the F-UVMS. The motion experiments of the F-UVMS are conducted in the sea and the motion patterns of the F-UVMS are validated.

关键词： data driven modeling underwater vehicle-manipulator system underwater biomimetic vehicle hydrodynamic modeling

来源：评论

学校读者我要写书评

暂无评论

Corrosion test improvement by data driven climatic modeling

引用

MATERIALS AND CORROSION-WERKSTOFFE UND KORROSION 2017年第12期68卷 1338-1342页

作者： Mayrhofer, R. Baeck, T. Mercedes Benz Werk Sindelfingen D-71059 Sindelfingen Germany Leiden Univ Leiden Inst Adv Comp Sci Ca Leiden Netherlands Divis Intelligent Solut GmbH Joseph von Fraunhofer Str 20 Dortmund Germany

Many corrosion test experiments, using a range of testing methods and car body materials, are done by the automotive industry worldwide to meet the corrosion requirements in the field. In this paper, we use test data and climate field data for data driven modeling of the test results. One contribution reported here is to find the most influencing factors for corrosion test progress and field correlation. Therefore, iron and zinc panels with automotive paintings conducted in several corrosion tests are measured and transformed into suitable data. The corrosion parameters are defined as factors and the result of corrosion testing (i.e., scribe creepage values) as output variable. With this data, a statistical model is generated and validated. The best fit model is analyzed to find sensible testing parameters effecting the corrosion results. The same procedure is also applied for climatic field data, which is first transformed into characteristics such as humidity, duration of wetness, and salt load. The data from corrosion testing experiments are then mapped to the climatic load in the field. A match to the field correlation can be found, as demonstrated by our results.

关键词： corrosion test data driven modeling field data optimization predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Scalable data-driven modeling of spatio-temporal systems: Weather forecasting

引用

INTELLIGENT data ANALYSIS 2017年第3期21卷 577-595页

作者： Moshki, Mohsen Kabiri, Peyman Mohebalhojeh, Alireza Iran Univ Sci & Technol Sch Comp Engn Univ RdHengam StResalat Sq Tehran *** Iran Univ Tehran Inst Geophys Tehran Iran

In this paper, a new data-driven method for short-range forecasting of spatio-temporal systems is proposed. It uses NCEP data as raw data to construct forecasting model. The global model consists of several local models. Each local model is constructed in three steps. In the first step, a local dataset is constructed based on NCEP raw data. This dataset is a very high-dimensional data with huge number of redundant and irrelevant features. In the second step, a feature selection method named GRASP is applied on the local dataset and produces a new local dataset whose features are reduced significantly. In the third step, a regression ensemble method called Bagging is used to construct a local model. Both GRASP and Bagging methods are scalable modules with respect to the computational power needed. The proposed method makes it possible to control the trade-off between speed and precision. In addition to the scalability, the proposed method, in some points produces forecasts more precise than the GFS system.

关键词： Feature selection regression ensemble spatio-temporal modeling data driven modeling Numerical Weather Prediction

来源：评论

学校读者我要写书评

暂无评论

Progress in data-driven thermal comfort analysis and modeling

引用

ENERGY AND BUILDINGS 2025年 336卷

作者： Culic, Ana Nizetic, Sandro Gambiroza, Jelena Culic Solic, Petar Univ Split FESB Rudjera Boskov 32 Split 21000 Croatia Univ Split Fac Maritime Studies Rudjera Boskov 37 Split 21000 Croatia

Thermal comfort modeling has become increasingly reliant on data-driven approaches, utilizing the potential of machine learning algorithms to predict and improve indoor environmental quality. This paper provides a comprehensive review of methodologies and approaches employed in thermal comfort research, focusing on input variables, output predictions, applied algorithms, and performance evaluation metrics. The study systematically analyzes key environmental inputs, i.e. air temperature, mean radiant temperature, air velocity, and relative air humidity, along with physiological inputs including heart rate and skin temperature which are used to predict thermal comfort indicators, i.e. Thermal Comfort (TC), Thermal Preference (TP), Thermal Sensation (TS) and Predicted Mean Vote (PMV). A variety of machine learning algorithms, such as Random Forest, Support Vector Machine, Artificial Neural Networks, K-Nearest Neighbors have been applied in both regression and classification tasks. The assessment of thermal comfort models developed through the literature was carried out using common performance metrics;Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Accuracy, Precision, Recall and F1-score. The most common algorithms and performance metrics were considered from the reviewed papers and the best results are presented within the herein presented work reflecting the complexity of predicting personal thermal comfort. The paper also highlights the importance of dataset diversity, analyzing data sources from multiple geographical regions, including Europe, North America, and Asia. Finally, the future direction for thermal comfort modeling is discussed, emphasizing the need for developing a framework that can support the widespread application of thermal comfort models in energy-efficient building management systems.

关键词： Thermal comfort data driven modeling Smart buildings

来源：评论

学校读者我要写书评

暂无评论

Verification of Sinusoidal Steady State system identification of a Phantom Omni haptic device using data driven modeling 6

Verification of Sinusoidal Steady State system identificatio...

引用

6th International Conference on Automation, Robotics and Applications (ICARA)

作者： Milne, B. J. E. Beelen, H. P. G. J. Merks, R. W. H. Weiland, S. Chen, X. Q. Hann, C. E. Parker, R. J.

ISBN: (纸本)9781479964666

Haptic feedback has two important sources of dynamics: the machine being controlled and the haptic device itself. This paper concentrates on the means of identifying the dynamics of a Phantom Omni haptic feedback device. Two models are compared: a dynamic model with parameters using results from sinusoidal steady state analysis and a data driven model that uses pseudo-random binary sequences (PRBS) for identification. The overall form of the frequency and phase response is well-defined for the dynamics model but for the data driven model a spectral estimate from PRBS response data is used to determine the model order. The results in this paper show that a dynamic equation based minimal model produces accuracy as good as the data driven model. While the data driven model has more fitting accuracy the increase in accuracy is not useful for modelling the physical response as the differences occur at high frequencies where the Phantom arm is not sensitive anyway. The dynamic model is particularly useful as it gives a physical basis for the observed output and the sinusoidal steady state behaviour is useful for exposing non-linearities. Future work includes development and verification an arm inertia model that allows system parameters to be identified from response data at arbitrary arm angles.

关键词： System identification data driven modeling Minimal modeling

来源：评论

学校读者我要写书评

暂无评论

data driven modeling and Verification for Silicon Carbide JFET with Thermal Effects

Data Driven Modeling and Verification for Silicon Carbide JF...

引用

29th Annual IEEE Applied Power Electronics Conference and Exposition (APEC)

作者： Ruan Li-gang Zhu Ping Wang Li Nanjing Univ Aeronaut & Astronaut Dept Elect Engn Coll Automat Jiangsu Key Lab New Energy Generat & Power Conver Nanjing 210016 Jiangsu Peoples R China

ISBN: (纸本)9781479923250

A data driven model with thermal effects is proposed for normally-off SiC JFET in this paper. The novel feature of the model is that it saves the trouble of obtaining the physical parameters. Besides, the effect of temperature on SiC JFET performance is taken into account. It is important because the physical parameters on materials and dimensions of a particular SiC JFET device are difficult to be obtained for device users. The model is implemented based directly upon the characteristics of device datasheet and data from experimental tests. Simulation and experiments are carried out for the research of steady state characteristics, switching characteristics and short-circuit characteristics, which verify the accuracy of the model. Method of data driven modeling can be applied to the other power semiconductor switches.

关键词： junction gate field effect transistors power field effect transistors semiconductor device models silicon compounds wide band gap semiconductors SiC data driven modeling data driven verification physical parameters power semiconductor switches short-circuit characteristics silicon carbide JFET steady state characteristics switching characteristics thermal effects data models Integrated circuit modeling JFETs Junctions Silicon carbide Switches Temperature

来源：评论

学校读者我要写书评

暂无评论

data-driven insights for improved heating and cooling predictions: Impact of input parameters on multivariate deep learning algorithms using geothermal borehole field data

引用

APPLIED THERMAL ENGINEERING 2024年 245卷

作者： Ahmed, Naveed Assadi, Mohsen Zhang, Qian Sliwa, Tomasz Univ Stavanger Dept Energy & Petr Engn N-4021 Stavanger Norway Natl Univ Sci & Technol NUST US Pakistan Ctr Adv Studies Energy USPCASE H-12 Sect Islamabad 44000 Pakistan AGH Univ Sci & Technol Drilling Oil & Gas Fac Lab Geoenerget Mickiewicz Ave 30 PL-30059 Krakow Poland

The current research examines the effect of input parameters on the accuracy of deep learning models for forecasting borehole heat exchanger (BHE) temperatures. The study investigates the impact of different input parameters on the selection and performance of various multivariate deep AI models, such as LSTM, GRU, CNN, and BD-LSTM, within the context of geothermal borehole coupled heat pump systems. Real borehole-field data is used to train models with variable number of input parameters, aiming to predict 24-hour-ahead performance for meeting heating and cooling requirements. Key input parameters are identified using significance level test of Explainable AI techniques like Shapley Additive Explanations (SHAP) and sensitivity analysis was performed to assess their impact on model predictions. The results indicate that BD-LSTM outperforms other models in forecasting accuracy, followed by LSTM, GRU, and 1D -CNN, establishing BD-LSTM as the most accurate. The number of input parameters significantly affects forecasting accuracy, but more parameters do not necessarily improve performance. For instance, adding solar radiation as an input did not significantly alter BD-LSTM and BLSTM ' s forecasting accuracy, with MAPEs of 2.69% and 3.26%, respectively. Conversely, GRU ' s accuracy decreased (MAPE: 3.36%), while 1D-CNN ' s improved (MAPE: 2.92%). The SHAP analysis shows that the significance ranking of input parameters for the top-performing BD-LSTM model remains same for Case-1 and Case3 but with different impact of magnitude. The study concludes that the selection of practically measurable, relevant input parameters is vital for accurate temperature forecasting in geothermal applications, a finding that extends beyond existing research which often emphasizes algorithm selection over input parameter optimization.

关键词： Ground source heat pump Borehole coupled heat pump Heating and cooling Prediction model data driven modeling Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

data driven forest fire susceptibility mapping in Bangladesh

引用

ECOLOGICAL INDICATORS 2024年 166卷

作者： Haydar, Mafrid Rafi, Al Hossain Sadia, Halima Hossain, Md Tanvir Khulna Univ Engn & Technol KUET Dept Urban & Reg Planning Room 206 Khulna 9203 Bangladesh

Forests are essential natural resources that serve to facilitate economic activity while also providing an essential impact on climate regulation and the carbon cycle. In the Chittagong hill tracts, forest fires significantly contribute to the eradication of forests and the depletion of biodiversity. As a result, addressing the forest fire hazard is crucial for mitigating its potential negative effects. By implementing machine learning (ML) and deep learning (DL) algorithms, the primary aim of this research is to determine which areas within the CHT are most prone to forest fires. Artificial Neural Network (ANN), Classification and Regression Trees (CART), Categorical Boosting (Catboost), Convolutional Neural Network (CNN), Deep Neural Network (DNN), Gradient Boosting Decision Tree (GBDT), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGboost) are among these algorithms. This research investigates 267 past forest fire incidents while incorporating fifteen predictive parameters for forest fires. The utmost accuracy is demonstrated by the Catboost model, which has an AUC value of 0.83. Applied models the Bandarbon and Rangamati regions of the Chittagong hill tracts have been thoroughly analyzed and discovered to be extremely and moderately vulnerable to forest fires due to their intricate physical and social characteristics. The Catboost model indicates that 67.38% of the total regions and 0.59% of the regions in Chittagoong hill tracts are classified as moderate and high susceptible zones, respectively. The results of this study present the models utilized in the present analysis exhibit a high level of effectiveness. Furthermore, the findings indicated that the NDVI and annual temperature had the most influence. The application of both ML and DL approaches in the Chittagong hill tracts for the first time resulted in models that exhibited excellent accuracy and precision, combining perfectly with the actual conditions on the ground. Thi

关键词： Forest Fire Remote Sensing data driven modeling Machine Learning Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Using Deep Neural Networks and Big data to Predict Microscopic Travel Time in Work Zones

引用

TRANSPORTATION RESEARCH RECORD 2024年第10期2678卷 419-434页

作者： Morshedzadeh, Yeganeh Gargoum, Suliman Gargoum, Ali Univ British Columbia Sch Engn Vancouver BC V6T 1Z4 Canada United Arab Emirates Univ Dept Stat Al Ain U Arab Emirates

Traffic management in work zones is a challenging task that requires a balance between creating a safe environment for workers and minimizing traffic delays. Accurately predicting travel times through work zones is essential for dynamic traffic management and reducing congestion. However, complex interrupted traffic patterns in work zones (also known as construction zones) make this challenging compared with regular traffic congestion and free-flow conditions. To address this complexity, the paper develops a data-driven deep feed-forward artificial neural network to forecast under-construction travel times in work zones using an integrated data set of almost half a million observations. The variables considered in the neural network include the work zone characteristics, road design features, weather information, and traffic flow information. The raw data set comprised approximately 15 million travel time observations collected at 674 work zones. After cleaning and preprocessing the data and applying feature engineering techniques, the raw data set was reduced to 81 work zones spread along a 700 km corridor between the western borders of Alberta and Vancouver, British Columbia. The data were split into training and test data using a 90:10 ratio. Training data were used to develop a 27-input neural network with four hidden layers. After validating the test data, the neural network achieved a root mean squared error of 0.150 min and an R-squared score of 0.945, indicating a high accuracy level in estimating the under-construction travel time.

关键词： work zone delay time under construction travel time estimation artificial neural network non-recurrent traffic congestion data driven modeling operations interrupted flow travel time traffic flow theory and characteristics traffic flow

来源：评论

学校读者我要写书评

暂无评论

Optimal design, operational controls, and data-driven machine learning in sustainable borehole heat exchanger coupled heat pumps: Key implementation challenges and advancement opportunities

引用

ENERGY FOR SUSTAINABLE DEVELOPMENT 2023年第1期74卷 231-257页

作者： Ahmed, Naveed Assadi, Mohsen Ahmed, Abdelazim Abbas Banihabib, Reyhaneh Univ I Stavanger Dept Energy & Petr Engn N-4021 Stavanger Norway Natl Univ Sci & Technol NUST US Pakistan Ctr Adv Studies Energy USPCASE H 12 Sect Islamabad Pakistan

The integration of technologies has made it possible to develop optimal operating conditions at reduced costs, which results in a more sustainable energy transition away from fossil fuels and a step closer towards net-zero emission buildings (NZEB) for sustainable development. In recent years, ground source heat pump has gained recognition as an established thermal technology that can be integrated into smart energy systems to support the sudden rise in energy demand, flatten the quick changes in the supply side, and lower energy costs. On the user side, low-temperature heating and high-temperature cooling borehole coupled heat pumps (BCHP) have gained popularity due to its excellent performance in terms of energy efficiency, sustainability, and simplicity of inte-gration with renewable resources. As a green solution for building space heating/cooling, BCHP systems have the potential to considerably contribute to the CO2 reduction milestones, but they are still underutilized, mostly because of their high initial investment costs. The applications of automation, data retrieval, smart decision making, control optimization, modeling and monitoring, are recent areas where data driven AI algorithms are becoming increasingly significant. AI approaches can help BCHP become more intelligent and offer new op-portunities for studying heating and cooling systems. While much research is conducted to improve the design of borehole heat exchanger (BHEx) based heat pump, an efficient control approach is equally essential to achieving long-term performance and a shorter payback period. The objective of the current study is to identify the po-tential of most recent innovations in the field of data driven machine learning techniques to enhance BCHP operations and performance predictions to meet NZEBs. The explicit implementation challenges linked with BCHPs modeling are pointed out and the requirements needed for setting BCHP control algorithms are presented. Various methods found in

关键词： Ground source heat pump Borehole coupled heat pump Operational controls data driven modeling Artificial Intelligence Heating and cooling

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：